Uncover the Overhead and Resource Usage for Handling KV Cache Overflow in LLM Inference

Copy BibTeX

@misc{ye2024uncoveroverhead,
  grc_key = {ye2024uncoveroverhead},
  grc_slug = {ye-2024-uncover-overhead-3814},
  author = {Ye, J. and Nicolae, B. and Kougkas, A. and Sun, X.-H.},
  title = {{Uncover the Overhead and Resource Usage for Handling KV Cache Overflow in LLM Inference}},
  howpublished = {The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC'24)},
  year = {2024},
  month = nov,
  url = {http://cs.iit.edu/%7Escs/assets/files/ye2024kvcache_poster.pdf},
  source_url = {http://cs.iit.edu/%7Escs/assets/files/ye2024kvcache_poster.pdf},
  keywords = {KV Cache, LLM Inference},
}